Triple

T16378247
Position Surface form Disambiguated ID Type / Status
Subject Shardlake series E397731 entity
Predicate featuresCharacter P626 FINISHED
Object Barak
Barak is a tough, streetwise assistant and later close ally to Tudor lawyer-detective Matthew Shardlake in C. J. Sansom’s historical mystery series.
E1211002 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Barak | Statement: [Shardlake series, featuresCharacter, Barak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barak
Context triple: [Shardlake series, featuresCharacter, Barak]
  • A. Barak
    Barak is a biblical military leader in the Book of Judges who, alongside the prophetess Deborah, led Israel to victory over the Canaanite commander Sisera.
  • B. Avigdor
    Avigdor is a Hebrew given name of biblical origin, traditionally used in Jewish communities.
  • C. Natan
    Natan is a masculine given name of Hebrew origin, commonly used in Jewish and Israeli communities and meaning "he gave."
  • D. Ben-Tzvi
    Ben-Tzvi is a transliterated form of the Hebrew surname "Ben-Zvi," most notably associated with Yitzhak Ben-Zvi, the second President of Israel.
  • E. Benayahu
    Benayahu is a kabbalistic and halachic work by the Sephardic sage Ben Ish Chai, offering mystical and ethical commentary on Talmudic passages.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Barak
Triple: [Shardlake series, featuresCharacter, Barak]
Generated description
Barak is a tough, streetwise assistant and later close ally to Tudor lawyer-detective Matthew Shardlake in C. J. Sansom’s historical mystery series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Barak
Target entity description: Barak is a tough, streetwise assistant and later close ally to Tudor lawyer-detective Matthew Shardlake in C. J. Sansom’s historical mystery series.
  • A. Barak
    Barak is a biblical military leader in the Book of Judges who, alongside the prophetess Deborah, led Israel to victory over the Canaanite commander Sisera.
  • B. Avigdor
    Avigdor is a Hebrew given name of biblical origin, traditionally used in Jewish communities.
  • C. Natan
    Natan is a masculine given name of Hebrew origin, commonly used in Jewish and Israeli communities and meaning "he gave."
  • D. Ben-Tzvi
    Ben-Tzvi is a transliterated form of the Hebrew surname "Ben-Zvi," most notably associated with Yitzhak Ben-Zvi, the second President of Israel.
  • E. Benayahu
    Benayahu is a kabbalistic and halachic work by the Sephardic sage Ben Ish Chai, offering mystical and ethical commentary on Talmudic passages.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d87f2880b48190ae1a9673a3bbef80 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e319d97e00819094aa094f52a5a93e completed April 18, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00356658e881908131a3c60ed5499d completed May 10, 2026, 7:36 a.m.
NEDg Description generation batch_6a00383a7180819092ea605aa8ef1672 completed May 10, 2026, 7:48 a.m.
NED2 Entity disambiguation (via description) batch_6a00391645ac819092a06dc6813604fa completed May 10, 2026, 7:51 a.m.
Created at: April 10, 2026, 5:08 a.m.